AI Paper Atlas

Research map / Label-efficient and robust learning / Self-supervised and contrastive

A Theoretical Framework for Masked Pretraining (MPT)

Qi Zhang, Runyu Zhou, Yifei Wang, Yisen Wang

JMLR 2026 · Label-efficient and robust learning › Self-supervised and contrastive · approach: Masked autoencoder pretraining · 0 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add uniformity regularizerMAE · ImageNet-100 (ViT-Base) linear probingaccuracy: 61.2 -> 67.5Improved
add uniformity regularizerMAE · CIFAR-10 (ViT-Tiny) linear probingaccuracy: 59.6 -> 68.9Improved
add uniformity regularizerMAE · ImageNet-1K (ViT-Base) linear probingaccuracy: 55.4 -> 58.5Improved
add uniformity regularizerMAE · in-domain fine-tuning (CIFAR-10, ImageNet-100, ImageNet-1K)accuracy: 89.6 -> 89.4No clear effect
add uniformity regularizerMAE · iNaturalist-2021 fine-tuningaccuracy: 66.0 -> 69.4Improved
add uniformity regularizerMAE · CUB and Cars fine-tuningaccuracy: 81.5 -> 81.8; 59.8 -> 60.3Improved
add uniformity regularizerMAE · ImageNet-C Defocus Blur linear probingaccuracy: 10.48 -> 26.20Improved
add uniformity regularizerMAE · ImageNet-A linear probing (frozen)accuracy: 0.57 -> 0.68Improved
add uniformity lossSimMIM · ImageNet-100 linear probingaccuracy: 54.3 -> 61.1Improved
set uniformity coefficient to 0.01 instead of 0 (ablation)MAE (U-MPT) · ImageNet-100 linear probingaccuracy: 61.2 -> 67.5Improved
set uniformity coefficient to 1e-3 instead of 0 (ablation)MAE (U-MPT) · ImageNet-100 linear probingaccuracy: 61.2 -> 65.9Improved
raise uniformity coefficient to 0.1 from 0.01 (ablation)MAE (U-MPT) · ImageNet-100 linear probingaccuracy: 67.5 -> 45.1Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy